Convolutional Neural Networks

Project: Write an Algorithm for a Dog Identification App


In this notebook, some template code has already been provided for you, and you will need to implement additional functionality to successfully complete this project. You will not need to modify the included code beyond what is requested. Sections that begin with '(IMPLEMENTATION)' in the header indicate that the following block of code will require additional functionality which you must provide. Instructions will be provided for each section, and the specifics of the implementation are marked in the code block with a 'TODO' statement. Please be sure to read the instructions carefully!

Note: Once you have completed all of the code implementations, you need to finalize your work by exporting the Jupyter Notebook as an HTML document. Before exporting the notebook to html, all of the code cells need to have been run so that reviewers can see the final implementation and output. You can then export the notebook by using the menu above and navigating to File -> Download as -> HTML (.html). Include the finished document along with this notebook as your submission.

In addition to implementing code, there will be questions that you must answer which relate to the project and your implementation. Each section where you will answer a question is preceded by a 'Question X' header. Carefully read each question and provide thorough answers in the following text boxes that begin with 'Answer:'. Your project submission will be evaluated based on your answers to each of the questions and the implementation you provide.

Note: Code and Markdown cells can be executed using the Shift + Enter keyboard shortcut. Markdown cells can be edited by double-clicking the cell to enter edit mode.

The rubric contains optional "Stand Out Suggestions" for enhancing the project beyond the minimum requirements. If you decide to pursue the "Stand Out Suggestions", you should include the code in this Jupyter notebook.


Why We're Here

In this notebook, you will make the first steps towards developing an algorithm that could be used as part of a mobile or web app. At the end of this project, your code will accept any user-supplied image as input. If a dog is detected in the image, it will provide an estimate of the dog's breed. If a human is detected, it will provide an estimate of the dog breed that is most resembling. The image below displays potential sample output of your finished project (... but we expect that each student's algorithm will behave differently!).

Sample Dog Output

In this real-world setting, you will need to piece together a series of models to perform different tasks; for instance, the algorithm that detects humans in an image will be different from the CNN that infers dog breed. There are many points of possible failure, and no perfect algorithm exists. Your imperfect solution will nonetheless create a fun user experience!

The Road Ahead

We break the notebook into separate steps. Feel free to use the links below to navigate the notebook.

  • Step 0: Import Datasets
  • Step 1: Detect Humans
  • Step 2: Detect Dogs
  • Step 3: Create a CNN to Classify Dog Breeds (from Scratch)
  • Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)
  • Step 5: Write your Algorithm
  • Step 6: Test Your Algorithm

Step 0: Import Datasets

Make sure that you've downloaded the required human and dog datasets:

Note: if you are using the Udacity workspace, you DO NOT need to re-download these - they can be found in the /data folder as noted in the cell below.

  • Download the dog dataset. Unzip the folder and place it in this project's home directory, at the location /dog_images.

  • Download the human dataset. Unzip the folder and place it in the home directory, at location /lfw.

Note: If you are using a Windows machine, you are encouraged to use 7zip to extract the folder.

In the code cell below, we save the file paths for both the human (LFW) dataset and dog dataset in the numpy arrays human_files and dog_files.

In [1]:
import numpy as np
from glob import glob

# load filenames for human and dog images
human_files = np.array(glob("/data/lfw/*/*"))
dog_files = np.array(glob("/data/dog_images/*/*/*"))

# print number of images in each dataset
print('There are %d total human images.' % len(human_files))
print('There are %d total dog images.' % len(dog_files))
There are 13233 total human images.
There are 8351 total dog images.

Step 1: Detect Humans

In this section, we use OpenCV's implementation of Haar feature-based cascade classifiers to detect human faces in images.

OpenCV provides many pre-trained face detectors, stored as XML files on github. We have downloaded one of these detectors and stored it in the haarcascades directory. In the next code cell, we demonstrate how to use this detector to find human faces in a sample image.

In [2]:
import cv2                
import matplotlib.pyplot as plt                        
%matplotlib inline                               

# extract pre-trained face detector
face_cascade = cv2.CascadeClassifier('haarcascades/haarcascade_frontalface_alt.xml')

# load color (BGR) image
img = cv2.imread(human_files[0])
# convert BGR image to grayscale
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

# find faces in image
faces = face_cascade.detectMultiScale(gray)

# print number of faces detected in the image
print('Number of faces detected:', len(faces))

# get bounding box for each detected face
for (x,y,w,h) in faces:
    # add bounding box to color image
    cv2.rectangle(img,(x,y),(x+w,y+h),(255,0,0),2)
    
# convert BGR image to RGB for plotting
cv_rgb = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)

# display the image, along with bounding box
plt.imshow(cv_rgb)
plt.show()
Number of faces detected: 1

Before using any of the face detectors, it is standard procedure to convert the images to grayscale. The detectMultiScale function executes the classifier stored in face_cascade and takes the grayscale image as a parameter.

In the above code, faces is a numpy array of detected faces, where each row corresponds to a detected face. Each detected face is a 1D array with four entries that specifies the bounding box of the detected face. The first two entries in the array (extracted in the above code as x and y) specify the horizontal and vertical positions of the top left corner of the bounding box. The last two entries in the array (extracted here as w and h) specify the width and height of the box.

Write a Human Face Detector

We can use this procedure to write a function that returns True if a human face is detected in an image and False otherwise. This function, aptly named face_detector, takes a string-valued file path to an image as input and appears in the code block below.

In [3]:
# returns "True" if face is detected in image stored at img_path
def face_detector(img_path):
    img = cv2.imread(img_path)
    gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
    faces = face_cascade.detectMultiScale(gray)
    return len(faces) > 0

(IMPLEMENTATION) Assess the Human Face Detector

Question 1: Use the code cell below to test the performance of the face_detector function.

  • What percentage of the first 100 images in human_files have a detected human face?
  • What percentage of the first 100 images in dog_files have a detected human face?

Ideally, we would like 100% of human images with a detected face and 0% of dog images with a detected face. You will see that our algorithm falls short of this goal, but still gives acceptable performance. We extract the file paths for the first 100 images from each of the datasets and store them in the numpy arrays human_files_short and dog_files_short.

Answer: (You can print out your results and/or write your percentages in this cell)

In [4]:
from tqdm import tqdm

human_files_short = human_files[:100]
dog_files_short = dog_files[:100]

#-#-# Do NOT modify the code above this line. #-#-#

## TODO: Test the performance of the face_detector algorithm 
## on the images in human_files_short and dog_files_short.
human_test = sum([face_detector(i) for i in human_files_short])

dog_test = sum([face_detector(i) for i in dog_files_short])

print('human files result: ', human_test)
print('dog files result: ', dog_test)
human files result:  98
dog files result:  17

We suggest the face detector from OpenCV as a potential way to detect human images in your algorithm, but you are free to explore other approaches, especially approaches that make use of deep learning :). Please use the code cell below to design and test your own face detection algorithm. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.

In [5]:
### (Optional) 
### TODO: Test performance of anotherface detection algorithm.
### Feel free to use as many code cells as needed.

Step 2: Detect Dogs

In this section, we use a pre-trained model to detect dogs in images.

Obtain Pre-trained VGG-16 Model

The code cell below downloads the VGG-16 model, along with weights that have been trained on ImageNet, a very large, very popular dataset used for image classification and other vision tasks. ImageNet contains over 10 million URLs, each linking to an image containing an object from one of 1000 categories.

In [4]:
import torch
import torchvision.models as models

# define VGG16 model
VGG16 = models.vgg16(pretrained=True)

# check if CUDA is available
use_cuda = torch.cuda.is_available()

# move model to GPU if CUDA is available
if use_cuda:
    VGG16 = VGG16.cuda()

Given an image, this pre-trained VGG-16 model returns a prediction (derived from the 1000 possible categories in ImageNet) for the object that is contained in the image.

(IMPLEMENTATION) Making Predictions with a Pre-trained Model

In the next code cell, you will write a function that accepts a path to an image (such as 'dogImages/train/001.Affenpinscher/Affenpinscher_00001.jpg') as input and returns the index corresponding to the ImageNet class that is predicted by the pre-trained VGG-16 model. The output should always be an integer between 0 and 999, inclusive.

Before writing the function, make sure that you take the time to learn how to appropriately pre-process tensors for pre-trained models in the PyTorch documentation.

In [5]:
from PIL import Image
import torchvision.transforms as transforms

def VGG16_predict(img_path):
    '''
    Use pre-trained VGG-16 model to obtain index corresponding to 
    predicted ImageNet class for image at specified path
    
    Args:
        img_path: path to an image
        
    Returns:
        Index corresponding to VGG-16 model's prediction
    '''
    
    ## TODO: Complete the function.
    ## Load and pre-process an image from the given img_path
    ## Return the *index* of the predicted class for that image
    
    #Open the image
    img = Image.open(img_path)
    #transform img to tensor to feed into the vgg16 model
    toTensor = transforms.ToTensor()
    #resize all images to 250 h and w
    transformation = transforms.Compose([transforms.RandomResizedCrop(224),
                                         transforms.ToTensor(),
                                         transforms.Normalize([0.485, 0.456, 0.406],
                                                               [0.229, 0.224, 0.225])])
    
    img_tensor = transformation(img)
    img_tensor = img_tensor.unsqueeze(0)
    
    #move to cuda if available
    if torch.cuda.is_available():
        img_tensor = img_tensor.cuda()
    
    prediction = VGG16(img_tensor)
    
    #cpu processing
    if torch.cuda.is_available():
        prediction = prediction.cpu()
        
    index = prediction.data.numpy().argmax()
    
    return index # predicted class index
In [6]:
def process_image_to_tensor(image):
    ''' Scales, crops, and normalizes a PIL image for a PyTorch model,
        returns a tensor array
    As per Pytorch documentations: All pre-trained models expect input images normalized in the same way, 
    i.e. mini-batches of 3-channel RGB images
    of shape (3 x H x W), where H and W are expected to be at least 224. 
    The images have to be loaded in to a range of [0, 1] and 
    then normalized using mean = [0.485, 0.456, 0.406] and std = [0.229, 0.224, 0.225]. 
    You can use the following transform to normalize:
    '''
    # define transforms for the training data and testing data
    prediction_transforms = transforms.Compose([transforms.Resize(224),
                                          transforms.CenterCrop(224),
                                          transforms.ToTensor(),
                                          transforms.Normalize([0.485, 0.456, 0.406],
                                                               [0.229, 0.224, 0.225])])
    
    img_pil = Image.open( image ).convert('RGB')
    img_tensor = prediction_transforms( img_pil )[:3,:,:].unsqueeze(0)
    
    return img_tensor


# helper function for un-normalizing an image  - from STYLE TRANSFER exercise
# and converting it from a Tensor image to a NumPy image for display
def image_convert(tensor):
    """ Display a tensor as an image. """
    
    image = tensor.to("cpu").clone().detach()
    image = image.numpy().squeeze()
    image = image.transpose(1,2,0)
    image = image * np.array((0.229, 0.224, 0.225)) + np.array((0.485, 0.456, 0.406))
    image = image.clip(0, 1)

    return image

(IMPLEMENTATION) Write a Dog Detector

While looking at the dictionary, you will notice that the categories corresponding to dogs appear in an uninterrupted sequence and correspond to dictionary keys 151-268, inclusive, to include all categories from 'Chihuahua' to 'Mexican hairless'. Thus, in order to check to see if an image is predicted to contain a dog by the pre-trained VGG-16 model, we need only check if the pre-trained model predicts an index between 151 and 268 (inclusive).

Use these ideas to complete the dog_detector function below, which returns True if a dog is detected in an image (and False if not).

In [7]:
### returns "True" if a dog is detected in the image stored at img_path
def dog_detector(img_path):
    ## TODO: Complete the function.
    
    index = VGG16_predict(img_path)
        
     
    return (151 <= index and index <= 268) # true/false
In [10]:
import cv2
import matplotlib.pyplot as plt                        
%matplotlib inline 

test = np.array(glob("test_files/*"))
print('There are %d total images.' % len(test))

for i in test:
    RGB_img = cv2.cvtColor(cv2.imread(i), cv2.COLOR_BGR2RGB)
    plt.imshow(RGB_img)
    plt.show()

dog_test = sum([dog_detector(i) for i in test])
    
print('dog files result: ', dog_test)
There are 11 total images.
dog files result:  7
In [8]:
dog_test = sum([dog_detector(i) for file in np.hstack((dog_files[:3]))])
    
print('dog files result: ', dog_test)
---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-8-2a17783ec639> in <module>()
      1 
----> 2 dog_test = sum([dog_detector(i) for file in np.hstack((dog_files[:3]))])
      3 
      4 print('dog files result: ', dog_test)

<ipython-input-8-2a17783ec639> in <listcomp>(.0)
      1 
----> 2 dog_test = sum([dog_detector(i) for file in np.hstack((dog_files[:3]))])
      3 
      4 print('dog files result: ', dog_test)

NameError: name 'i' is not defined

(IMPLEMENTATION) Assess the Dog Detector

Question 2: Use the code cell below to test the performance of your dog_detector function.

  • What percentage of the images in human_files_short have a detected dog?
  • What percentage of the images in dog_files_short have a detected dog?

Answer:

In [12]:
### TODO: Test the performance of the dog_detector function
### on the images in human_files_short and dog_files_short.

from tqdm import tqdm

human_files_short = human_files[:100]
dog_files_short = dog_files[:100]

#-#-# Do NOT modify the code above this line. #-#-#

## TODO: Test the performance of the face_detector algorithm 
## on the images in human_files_short and dog_files_short.
human_test = sum([dog_detector(i) for i in human_files_short])

dog_test = sum([dog_detector(i) for i in dog_files_short])

print('human files result: ', human_test)
print('dog files result: ', dog_test)
human files result:  0
dog files result:  95

We suggest VGG-16 as a potential network to detect dog images in your algorithm, but you are free to explore other pre-trained networks (such as Inception-v3, ResNet-50, etc). Please use the code cell below to test other pre-trained PyTorch models. If you decide to pursue this optional task, report performance on human_files_short and dog_files_short.

In [13]:
### (Optional) 
### TODO: Report the performance of another pre-trained network.
### Feel free to use as many code cells as needed.

Step 3: Create a CNN to Classify Dog Breeds (from Scratch)

Now that we have functions for detecting humans and dogs in images, we need a way to predict breed from images. In this step, you will create a CNN that classifies dog breeds. You must create your CNN from scratch (so, you can't use transfer learning yet!), and you must attain a test accuracy of at least 10%. In Step 4 of this notebook, you will have the opportunity to use transfer learning to create a CNN that attains greatly improved accuracy.

We mention that the task of assigning breed to dogs from images is considered exceptionally challenging. To see why, consider that even a human would have trouble distinguishing between a Brittany and a Welsh Springer Spaniel.

Brittany Welsh Springer Spaniel

It is not difficult to find other dog breed pairs with minimal inter-class variation (for instance, Curly-Coated Retrievers and American Water Spaniels).

Curly-Coated Retriever American Water Spaniel

Likewise, recall that labradors come in yellow, chocolate, and black. Your vision-based algorithm will have to conquer this high intra-class variation to determine how to classify all of these different shades as the same breed.

Yellow Labrador Chocolate Labrador Black Labrador

We also mention that random chance presents an exceptionally low bar: setting aside the fact that the classes are slightly imabalanced, a random guess will provide a correct answer roughly 1 in 133 times, which corresponds to an accuracy of less than 1%.

Remember that the practice is far ahead of the theory in deep learning. Experiment with many different architectures, and trust your intuition. And, of course, have fun!

(IMPLEMENTATION) Specify Data Loaders for the Dog Dataset

Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dog_images/train, dog_images/valid, and dog_images/test, respectively). You may find this documentation on custom datasets to be a useful resource. If you are interested in augmenting your training and/or validation data, check out the wide variety of transforms!

In [9]:
import os
from torchvision import datasets

from PIL import ImageFile

ImageFile.LOAD_TRUNCATED_IMAGES = True

### TODO: Write data loaders for training, validation, and test sets
## Specify appropriate transforms, and batch_sizes
transform = transforms.ToTensor()
batch_size = 20

train_transforms = transforms.Compose([transforms.Resize(224),
                                       transforms.CenterCrop(224),
                                       transforms.RandomHorizontalFlip(),
                                       transforms.RandomVerticalFlip(),
                                       transforms.RandomRotation(20),
                                       transforms.ToTensor(),
                                       transforms.Normalize([0.485, 0.456, 0.406],
                                                            [0.229, 0.224, 0.225])])

test_transforms = transforms.Compose([transforms.Resize(224),
                                      transforms.CenterCrop(224),
                                      transforms.ToTensor(),
                                      transforms.Normalize([0.485, 0.456, 0.406],
                                                           [0.229, 0.224, 0.225])])

train_data = datasets.ImageFolder('/data/dog_images/train', transform = train_transforms)
validation_data = datasets.ImageFolder('/data/dog_images/valid', transform = test_transforms)
test_data = datasets.ImageFolder('/data/dog_images/test', transform = test_transforms)

train_loader = torch.utils.data.DataLoader(train_data, batch_size=batch_size, shuffle = True)

validation_loader = torch.utils.data.DataLoader(validation_data, batch_size=batch_size)

test_loader = torch.utils.data.DataLoader(test_data, batch_size=batch_size)


# create dictionary for all loaders in one
loaders_scratch = {}
loaders_scratch['train'] = train_loader
loaders_scratch['valid'] = validation_loader
loaders_scratch['test'] = test_loader

Question 3: Describe your chosen procedure for preprocessing the data.

  • How does your code resize the images (by cropping, stretching, etc)? What size did you pick for the input tensor, and why?
  • Did you decide to augment the dataset? If so, how (through translations, flips, rotations, etc)? If not, why not?

Answer:

I chose to resize all data images by cropping using a center crop transformation. The chosen size for my input tensor is 2242243 which is chosen based on my research as 224*224 is a suitable input size in our case with depth of 3 as it's colored image inputs.

I made some augmentation on the training data set using some random horizontal and vertical flips, also used some random rotations to help the model generalize better.

(IMPLEMENTATION) Model Architecture

Create a CNN to classify dog breed. Use the template in the code cell below.

In [10]:
import torch.nn as nn
import torch.nn.functional as F

# define the CNN architecture
class Net(nn.Module):
    ### TODO: choose an architecture, and complete the class
    def __init__(self):
        super(Net, self).__init__()
        ## Define layers of a CNN
        self.conv1 = nn.Conv2d(3, 16, 3, padding = 1)
        self.conv2 = nn.Conv2d(16, 32, 3, padding = 1)
        self.conv3 = nn.Conv2d(32, 64, 3, padding = 1)
        self.conv4 = nn.Conv2d(64, 128, 3, padding = 1)
        
        self.fc = nn.Linear(14 * 14 * 128, 133)
        self.pool = nn.MaxPool2d(2,2)
        
    
    def forward(self, x):
        ## Define forward behavior
        x = F.relu(self.conv1(x))
        x = self.pool(x)
        x = F.relu(self.conv2(x))
        x = self.pool(x)
        x = F.relu(self.conv3(x))
        x = self.pool(x)
        x = F.relu(self.conv4(x))
        x = self.pool(x)
        
        x = x.view(x.size(0), -1)
        x = self.fc(x)
        return x

#-#-# You so NOT have to modify the code below this line. #-#-#

# instantiate the CNN
model_scratch = Net()
print(model_scratch)
# move tensors to GPU if CUDA is available
if use_cuda:
    model_scratch.cuda()
Net(
  (conv1): Conv2d(3, 16, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv2): Conv2d(16, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv3): Conv2d(32, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (conv4): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
  (fc): Linear(in_features=25088, out_features=133, bias=True)
  (pool): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
)

Question 4: Outline the steps you took to get to your final CNN architecture and your reasoning at each step.

Answer:

The first layer has input size of (224, 224, 3) and last layer should have the output size of 133 classes. I decided to create a simple CNN architecture, after some research I reached the final architecture which is: three convolutiona networks the first with depth of 16 the second with depth of 32 and the final with depth of 64. after each convolutional layer I add a maxpooling layer to reduce size by a factor of 2. finally I add fully connected layer with 133 output features which is the number of dog breeds we have. I used a relu activation function for each convolutional layer.

(IMPLEMENTATION) Specify Loss Function and Optimizer

Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_scratch, and the optimizer as optimizer_scratch below.

In [11]:
import torch.optim as optim

### TODO: select loss function
criterion_scratch = nn.CrossEntropyLoss()

### TODO: select optimizer
optimizer_scratch = torch.optim.SGD(model_scratch.parameters(), lr = 0.01)

(IMPLEMENTATION) Train and Validate the Model

Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_scratch.pt'.

In [12]:
def train(n_epochs, loaders, model, optimizer, criterion, use_cuda, save_path):
    """returns trained model"""
    # initialize tracker for minimum validation loss
    valid_loss_min = np.Inf 
    
    for epoch in range(1, n_epochs+1):
        # initialize variables to monitor training and validation loss
        train_loss = 0.0
        valid_loss = 0.0
        
        ###################
        # train the model #
        ###################
        model.train()
        for batch_idx, (data, target) in enumerate(loaders['train']):
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            ## find the loss and update the model parameters accordingly
            ## record the average training loss, using something like
            ## train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
            
            optimizer.zero_grad()
            
            output = model(data)
            
            loss = criterion(output, target)
            
            loss.backward()
            
            optimizer.step()
            
            #train_loss = train_loss + ((1 / (batch_idx + 1)) * (loss.data - train_loss))
            train_loss += loss.item()*data.size(0)
        ######################    
        # validate the model #
        ######################
        model.eval()
        for batch_idx, (data, target) in enumerate(loaders['valid']):
            # move to GPU
            if use_cuda:
                data, target = data.cuda(), target.cuda()
            ## update the average validation loss
            
            output = model(data)
            
            loss = criterion(output, target)
             
            valid_loss += loss.item() * data.size(0)
            
        # calculate average losses
        train_loss = train_loss / len(loaders['train'].dataset)
        valid_loss = valid_loss / len(loaders['valid'].dataset)

            
        # print training/validation statistics 
        print('Epoch: {} \tTraining Loss: {:.6f} \tValidation Loss: {:.6f}'.format(
            epoch, 
            train_loss,
            valid_loss
            ))
        
        ## TODO: save the model if validation loss has decreased
        if valid_loss <= valid_loss_min:
            print('Validation loss decreased ({:.6f} --> {:.6f}).  Saving model ...'.format(
            valid_loss_min,
            valid_loss))
            torch.save(model.state_dict(), save_path)
            valid_loss_min = valid_loss
            
    # return trained model
    return model
In [13]:
# train the model
model_scratch = train(12, loaders_scratch, model_scratch, optimizer_scratch, 
                      criterion_scratch, use_cuda, 'model_scratch.pt')

# load the model that got the best validation accuracy
model_scratch.load_state_dict(torch.load('model_scratch.pt'))
Epoch: 1 	Training Loss: 4.874540 	Validation Loss: 4.843185
Validation loss decreased (inf --> 4.843185).  Saving model ...
Epoch: 2 	Training Loss: 4.781218 	Validation Loss: 4.710791
Validation loss decreased (4.843185 --> 4.710791).  Saving model ...
Epoch: 3 	Training Loss: 4.600983 	Validation Loss: 4.575699
Validation loss decreased (4.710791 --> 4.575699).  Saving model ...
Epoch: 4 	Training Loss: 4.447058 	Validation Loss: 4.494873
Validation loss decreased (4.575699 --> 4.494873).  Saving model ...
Epoch: 5 	Training Loss: 4.353622 	Validation Loss: 4.466421
Validation loss decreased (4.494873 --> 4.466421).  Saving model ...
Epoch: 6 	Training Loss: 4.265435 	Validation Loss: 4.414853
Validation loss decreased (4.466421 --> 4.414853).  Saving model ...
Epoch: 7 	Training Loss: 4.173775 	Validation Loss: 4.422612
Epoch: 8 	Training Loss: 4.105020 	Validation Loss: 4.309897
Validation loss decreased (4.414853 --> 4.309897).  Saving model ...
Epoch: 9 	Training Loss: 4.016735 	Validation Loss: 4.531015
Epoch: 10 	Training Loss: 3.920142 	Validation Loss: 4.233451
Validation loss decreased (4.309897 --> 4.233451).  Saving model ...
Epoch: 11 	Training Loss: 3.829007 	Validation Loss: 4.291148
Epoch: 12 	Training Loss: 3.741621 	Validation Loss: 4.189762
Validation loss decreased (4.233451 --> 4.189762).  Saving model ...
In [ ]:
 

(IMPLEMENTATION) Test the Model

Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 10%.

In [14]:
def test(loaders, model, criterion, use_cuda):

    # monitor test loss and accuracy
    test_loss = 0.
    correct = 0.
    total = 0.

    model.eval()
    for batch_idx, (data, target) in enumerate(loaders['test']):
        # move to GPU
        if use_cuda:
            data, target = data.cuda(), target.cuda()
        # forward pass: compute predicted outputs by passing inputs to the model
        #with torch.no_grad():
        output = model(data)
        # calculate the loss
        loss = criterion(output, target)
        # update average test loss 
        test_loss = test_loss + ((1 / (batch_idx + 1)) * (loss.data - test_loss))
        # convert output probabilities to predicted class
        pred = output.data.max(1, keepdim=True)[1]
        # compare predictions to true label
        correct += np.sum(np.squeeze(pred.eq(target.data.view_as(pred))).cpu().numpy())
        total += data.size(0)
            
    print('Test Loss: {:.6f}\n'.format(test_loss))

    print('\nTest Accuracy: %2d%% (%2d/%2d)' % (
        100. * correct / total, correct, total))
In [15]:
# call test function    
test(loaders_scratch, model_scratch, criterion_scratch, use_cuda)
Test Loss: 4.195395


Test Accuracy:  8% (72/836)

Step 4: Create a CNN to Classify Dog Breeds (using Transfer Learning)

You will now use transfer learning to create a CNN that can identify dog breed from images. Your CNN must attain at least 60% accuracy on the test set.

(IMPLEMENTATION) Specify Data Loaders for the Dog Dataset

Use the code cell below to write three separate data loaders for the training, validation, and test datasets of dog images (located at dogImages/train, dogImages/valid, and dogImages/test, respectively).

If you like, you are welcome to use the same data loaders from the previous step, when you created a CNN from scratch.

In [21]:
import os
from torchvision import datasets

from PIL import ImageFile

ImageFile.LOAD_TRUNCATED_IMAGES = True

### TODO: Write data loaders for training, validation, and test sets
## Specify appropriate transforms, and batch_sizes
transform = transforms.ToTensor()
batch_size = 20

train_transforms = transforms.Compose([transforms.Resize(224),
                                       transforms.CenterCrop(224),
                                       transforms.RandomHorizontalFlip(),
                                       transforms.RandomVerticalFlip(),
                                       transforms.RandomRotation(20),
                                       transforms.ToTensor(),
                                       transforms.Normalize([0.485, 0.456, 0.406],
                                                            [0.229, 0.224, 0.225])])

test_transforms = transforms.Compose([transforms.Resize(224),
                                      transforms.CenterCrop(224),
                                      transforms.ToTensor(),
                                      transforms.Normalize([0.485, 0.456, 0.406],
                                                           [0.229, 0.224, 0.225])])

## TODO: Specify data loaders
trainData = datasets.ImageFolder('/data/dog_images/train', transform = train_transforms)
validData = datasets.ImageFolder('/data/dog_images/valid', transform = test_transforms)
testData = datasets.ImageFolder('/data/dog_images/test', transform = test_transforms)

trainLoader = torch.utils.data.DataLoader(trainData, batch_size=batch_size, shuffle = True)

validLoader = torch.utils.data.DataLoader(validData, batch_size=batch_size)

testLoader = torch.utils.data.DataLoader(testData, batch_size=batch_size)


# create dictionary for all loaders in one
loaders_transfer = {}
loaders_transfer['train'] = trainLoader
loaders_transfer['valid'] = validLoader
loaders_transfer['test'] = testLoader

(IMPLEMENTATION) Model Architecture

Use transfer learning to create a CNN to classify dog breed. Use the code cell below, and save your initialized model as the variable model_transfer.

In [22]:
for param in VGG16.features.parameters():
    param.requires_grad = False
    
print (VGG16)
VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace)
    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace)
    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace)
    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace)
    (2): Dropout(p=0.5)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace)
    (5): Dropout(p=0.5)
    (6): Linear(in_features=4096, out_features=1000, bias=True)
  )
)
In [23]:
import torchvision.models as models
import torch.nn as nn
import torch.nn as nn
import torch.nn.functional as F
## TODO: Specify model architecture 

n_inputs = VGG16.classifier[6].in_features
last_layer = nn.Linear(n_inputs, 133)

VGG16.classifier[6] = last_layer

model_transfer = VGG16

# after completing your model, if GPU is available, move the model to GPU
print(model_transfer.classifier[6].out_features)

print (model_transfer)
if use_cuda:
    model_transfer = model_transfer.cuda()
133
VGG(
  (features): Sequential(
    (0): Conv2d(3, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (1): ReLU(inplace)
    (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (3): ReLU(inplace)
    (4): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (5): Conv2d(64, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (6): ReLU(inplace)
    (7): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (8): ReLU(inplace)
    (9): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (10): Conv2d(128, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (11): ReLU(inplace)
    (12): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (13): ReLU(inplace)
    (14): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (15): ReLU(inplace)
    (16): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (17): Conv2d(256, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (18): ReLU(inplace)
    (19): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (20): ReLU(inplace)
    (21): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (22): ReLU(inplace)
    (23): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
    (24): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (25): ReLU(inplace)
    (26): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (27): ReLU(inplace)
    (28): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1))
    (29): ReLU(inplace)
    (30): MaxPool2d(kernel_size=2, stride=2, padding=0, dilation=1, ceil_mode=False)
  )
  (classifier): Sequential(
    (0): Linear(in_features=25088, out_features=4096, bias=True)
    (1): ReLU(inplace)
    (2): Dropout(p=0.5)
    (3): Linear(in_features=4096, out_features=4096, bias=True)
    (4): ReLU(inplace)
    (5): Dropout(p=0.5)
    (6): Linear(in_features=4096, out_features=133, bias=True)
  )
)

Question 5: Outline the steps you took to get to your final CNN architecture and your reasoning at each step. Describe why you think the architecture is suitable for the current problem.

Answer:

For the final CNN architecture, I used the pretrained VGG16 model with replacing the final layer with my fully connected layer to produce the required number of outputs which is 133. using pretrained models is very efficient as it reduces training time and produces better accuracy and better generalization of the model.

(IMPLEMENTATION) Specify Loss Function and Optimizer

Use the next code cell to specify a loss function and optimizer. Save the chosen loss function as criterion_transfer, and the optimizer as optimizer_transfer below.

In [26]:
import torch.optim as optim

criterion_transfer = nn.CrossEntropyLoss()
optimizer_transfer = optim.SGD(model_transfer.classifier.parameters(), lr=0.01)

(IMPLEMENTATION) Train and Validate the Model

Train and validate your model in the code cell below. Save the final model parameters at filepath 'model_transfer.pt'.

In [27]:
# train the model

model_transfer = train(8, loaders_transfer, model_transfer, optimizer_transfer, criterion_transfer, use_cuda, 'model_transfer.pt')

# load the model that got the best validation accuracy (uncomment the line below)
model_transfer.load_state_dict(torch.load('model_transfer.pt'))
Epoch: 1 	Training Loss: 2.497686 	Validation Loss: 0.790682
Validation loss decreased (inf --> 0.790682).  Saving model ...
Epoch: 2 	Training Loss: 1.591027 	Validation Loss: 0.649130
Validation loss decreased (0.790682 --> 0.649130).  Saving model ...
Epoch: 3 	Training Loss: 1.293275 	Validation Loss: 0.598728
Validation loss decreased (0.649130 --> 0.598728).  Saving model ...
Epoch: 4 	Training Loss: 1.163685 	Validation Loss: 0.512940
Validation loss decreased (0.598728 --> 0.512940).  Saving model ...
Epoch: 5 	Training Loss: 1.083422 	Validation Loss: 0.555784
Epoch: 6 	Training Loss: 0.993746 	Validation Loss: 0.514540
Epoch: 7 	Training Loss: 0.910824 	Validation Loss: 0.520546
Epoch: 8 	Training Loss: 0.862545 	Validation Loss: 0.476984
Validation loss decreased (0.512940 --> 0.476984).  Saving model ...
In [ ]:
 

(IMPLEMENTATION) Test the Model

Try out your model on the test dataset of dog images. Use the code cell below to calculate and print the test loss and accuracy. Ensure that your test accuracy is greater than 60%.

In [28]:
test(loaders_transfer, model_transfer, criterion_transfer, use_cuda)
Test Loss: 0.573604


Test Accuracy: 82% (692/836)

(IMPLEMENTATION) Predict Dog Breed with the Model

Write a function that takes an image path as input and returns the dog breed (Affenpinscher, Afghan hound, etc) that is predicted by your model.

In [ ]:
 
In [44]:
### TODO: Write a function that takes a path to an image as input
### and returns the dog breed that is predicted by the model.

# list of class names by index, i.e. a name can be accessed like class_names[0]
class_names = [item[4:].replace("_", " ") for item in trainData.classes]

def predict_breed_transfer(img_path):
    # load the image and return the predicted breed

    image_tensor = process_image_to_tensor(img_path)
    
    if use_cuda:
        image_tensor = image_tensor.cuda()
    
    model_transfer.eval()
    # get sample outputs
    with torch.no_grad():
        output = model_transfer(image_tensor)
        prediction = torch.argmax(output).item()
    #
    model_transfer.train()
    #output = model_transfer(image_tensor)
    # convert output probabilities to predicted class
    #_, preds_tensor = torch.max(output, 1)
    #pred = np.squeeze(preds_tensor.numpy()) if not use_cuda else np.squeeze(preds_tensor.cpu().numpy())
    
    return class_names[prediction]

def display_image(img_path, title="Title"):
    image = Image.open(img_path)
    plt.title(title)
    plt.imshow(image)
    plt.show()

#print (class_names)
In [45]:
import random
from PIL import Image, ImageFile 

dog_files_short = dog_files[:100]

for image in random.sample(list(dog_files_short), 4): 
    predicted_breed = predict_breed_transfer(image)
    display_image(image, title = predicted_breed)
In [46]:
## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.
test = np.array(glob("dog_test_pics/*"))
print('There are %d total images.' % len(test))

for image in test: 
    predicted_breed = predict_breed_transfer(image)
    display_image(image, title = predicted_breed)
There are 4 total images.

Step 5: Write your Algorithm

Write an algorithm that accepts a file path to an image and first determines whether the image contains a human, dog, or neither. Then,

  • if a dog is detected in the image, return the predicted breed.
  • if a human is detected in the image, return the resembling dog breed.
  • if neither is detected in the image, provide output that indicates an error.

You are welcome to write your own functions for detecting humans and dogs in images, but feel free to use the face_detector and human_detector functions developed above. You are required to use your CNN from Step 4 to predict dog breed.

Some sample output for our algorithm is provided below, but feel free to design your own user experience!

Sample Human Output

(IMPLEMENTATION) Write your Algorithm

In [47]:
'''
def run_app(img_path):
    ## handle cases for a human face, dog, and neither
    ImageFile.LOAD_TRUNCATED_IMAGES = True
    # check if image has juman faces:
    if (face_detector(img_path)):
        print("Hello Human!")
        predicted_breed = predict_breed_transfer(img_path)
        display_image(img_path, title="Predicted: {}".format(predicted_breed) )
        
        print("You look like a ...")
        print(predicted_breed)
        
    # check if image has dogs:
    elif dog_detector(img_path):
        print("Hello Dog!")
        predicted_breed = predict_breed_transfer(img_path)
        display_image(img_path, title="Predicted: {}".format(predicted_breed) )
        
        print("Your breed is most likley ...")
        print(predicted_breed)
    # otherwise
    else:
        print("Oh, we're sorry! We couldn't detect any dog or human face in the image.")
        display_image(img_path, title="...")
        print("Try another!")
        
    print("\n")
    
'''
In [32]:
### TODO: Write your algorithm.
### Feel free to use as many code cells as needed.

'''
def run_app(img_path):
    ## handle cases for a human face, dog, and neither
    if face_detector(img_path):
        print ('Hello, Human :), your resembling dog breed is: ')
        prediction = predict_breed_transfer(img_path)
        
        display_image(img_path, title="Predicted: {}".format(prediction) )
        #print(prediction)
    
    elif dog_detector(img_path):
        #print ('Hi Dog ;), your predicted breed is: ')
        #prediction = predict_breed_transfer(img_path)
        
        #for image in random.sample(list(dog_files_short), 4): 
        prediction = predict_breed_transfer(img_path)
        #display_image(img_path, title = prediction)
        display_image(img_path, title="Predicted: {}".format(prediction) )
        #print(prediciton)
        
        for image in img_path: 
            prediction = predict_breed_transfer(image)
            display_image(image, title = prediction)
        
    else:
        print('Error, no Dog or Human detected!')
        
        prediction = 'Null'
        display_image(img_path, title = prediction)
        #print(prediction)
    return prediction

'''
In [51]:
def run_app(img_path):
    ## handle cases for a human face, dog, and neither
    if face_detector(img_path):
        print('Hello Human!')
        plt.imshow(Image.open(img_path))
        plt.show()
        print(f'You look like a ... {predict_breed_transfer(img_path)}')
        print('\n-----------------------------------\n')
    elif dog_detector(img_path):
        plt.imshow(Image.open(img_path))
        plt.show()
        print(f'This is a picture of a ... {predict_breed_transfer(img_path)}')
        print('\n-----------------------------------\n')
    else:
        plt.imshow(Image.open(img_path))
        plt.show()
        print('Sorry, I did not detect a human or a dog in this image.')
        print('\n-----------------------------------\n')

Step 6: Test Your Algorithm

In this section, you will take your new algorithm for a spin! What kind of dog does the algorithm think that you look like? If you have a dog, does it predict your dog's breed accurately? If you have a cat, does it mistakenly think that your cat is a dog?

(IMPLEMENTATION) Test Your Algorithm on Sample Images!

Test your algorithm at least six images on your computer. Feel free to use any images you like. Use at least two human and two dog images.

Question 6: Is the output better than you expected :) ? Or worse :( ? Provide at least three possible points of improvement for your algorithm.

Answer: (Three possible points for improvement) I don't understand why the output is not detecting dogs? I tested the functions as you can see above but still get he same error of not detecting dogs even with trying different run_app function approaches!

In [33]:
## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.
test = np.array(glob("test_files/*"))
print('There are %d total images.' % len(test))

#for image in test: 
#    predicted_breed = predict_breed_transfer(image)
#    display_image(image, title = predicted_breed)

for i in test:
    RGB_img = cv2.cvtColor(cv2.imread(i), cv2.COLOR_BGR2RGB)
    #plt.imshow(RGB_img)
    #plt.show()
    run_app(i)
There are 11 total images.
Hello, Human :), your resembling dog breed is: 
Error, no Dog or Human detected!
Hello, Human :), your resembling dog breed is: 
Hello, Human :), your resembling dog breed is: 
Error, no Dog or Human detected!
Error, no Dog or Human detected!
Error, no Dog or Human detected!
Error, no Dog or Human detected!
Hello, Human :), your resembling dog breed is: 
Error, no Dog or Human detected!
Error, no Dog or Human detected!
In [52]:
## TODO: Execute your algorithm from Step 6 on
## at least 6 images on your computer.
## Feel free to use as many code cells as needed.

## suggested code, below
for file in np.hstack((human_files[:3], dog_files[:3])):
    run_app(file)
Hello Human!
You look like a ... German wirehaired pointer

-----------------------------------

Hello Human!
You look like a ... Bearded collie

-----------------------------------

Hello Human!
You look like a ... Portuguese water dog

-----------------------------------

Sorry, I did not detect a human or a dog in this image.

-----------------------------------

Sorry, I did not detect a human or a dog in this image.

-----------------------------------

Sorry, I did not detect a human or a dog in this image.

-----------------------------------

In [ ]: